Year: 2025
Type: preprint
Abstract: Speech tokenization is crucial in digital speech processing, converting continuous speech signals into discrete units for various computational tasks. This paper introduces a novel speech tokenizer with broad applicability across downstream tasks. While recent advances in residual vector quantization (RVQ) have incorporated semantic elements, they often neglect critical acoustic features. We propose an advanced approach that simultaneously encodes both linguistic and acoustic information, preserving prosodic and emotional content. Our method significantly enhances speech representation fidelity across diverse applications. Empirical evaluations demonstrate its effectiveness in speech coding, voice conversion, emotion recognition, and multimodal language modeling, without requiring additional training. This versatility underscores its potential as a key tool for advancing AI-driven speech processing.
Source: arXiv (Cornell University)
Authors: Jung, Wonjin, Kang, Sungil, Cho, Dong-Yeon
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416104208
Cites:
Cited by:
Related to: